Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1486 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0618. Min Range: -4.0618

Max Act: 4.0618. Min Act: -0.1700

Data Index: 5809054 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 4.0618. Min Range: -4.0618

Max Act: 4.0335. Min Act: -0.1700

Data Index: 2096261 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 4.0618. Min Range: -4.0618

Max Act: 4.0370. Min Act: -0.1700

Data Index: 7986133 (Open Web Text)

Max Activating Token Index: 211

Text #3

Max Range: 4.0618. Min Range: -4.0618

Max Act: 4.0054. Min Act: -0.1700

Data Index: 7472900 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 4.0618. Min Range: -4.0618

Max Act: 4.0263. Min Act: -0.1700

Data Index: 6096440 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 4.0618. Min Range: -4.0618

Max Act: 4.0099. Min Act: -0.1700

Data Index: 7700166 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9766. Min Act: -0.1700

Data Index: 6690843 (Open Web Text)

Max Activating Token Index: 65

Text #7

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9762. Min Act: -0.1700

Data Index: 1003086 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9881. Min Act: -0.1700

Data Index: 4636317 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9309. Min Act: -0.1700

Data Index: 6275610 (Open Web Text)

Max Activating Token Index: 502

Text #10

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9522. Min Act: -0.1700

Data Index: 4736031 (Open Web Text)

Max Activating Token Index: 671

Text #11

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9510. Min Act: -0.1700

Data Index: 2492158 (Open Web Text)

Max Activating Token Index: 1017

Text #12

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9482. Min Act: -0.1700

Data Index: 5974482 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9588. Min Act: -0.1700

Data Index: 7513114 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9438. Min Act: -0.1700

Data Index: 4907907 (Open Web Text)

Max Activating Token Index: 147

Text #15

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9353. Min Act: -0.1700

Data Index: 7823812 (Open Web Text)

Max Activating Token Index: 893

Text #16

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9501. Min Act: -0.1700

Data Index: 102898 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9424. Min Act: -0.1700

Data Index: 4573608 (Open Web Text)

Max Activating Token Index: 86

Text #18

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.9236. Min Act: -0.1700

Data Index: 1532876 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 4.0618. Min Range: -4.0618

Max Act: 3.8916. Min Act: -0.1700

Data Index: 5357950 (Open Web Text)

Max Activating Token Index: 47